Related papers: Efficient Self-supervised Vision Pretraining with …

Learned image compression (LIC) methods have experienced significant progress during recent years. However, these methods are primarily dedicated to optimizing the rate-distortion (R-D) performance at medium and high bitrates (> 0.1 bits…

Self-supervised learning approaches leverage unlabeled samples to acquire generic knowledge about different concepts, hence allowing for annotation-efficient downstream task learning. In this paper, we propose a novel self-supervised method…

Several recent works have directly extended the image masked autoencoder (MAE) with random masking into video domain, achieving promising results. However, unlike images, both spatial and temporal information are important for video…

Learning transferable representations from unlabeled time series is crucial for improving performance in data-scarce classification. Existing self-supervised methods often operate at the point level and rely on unidirectional encoding,…

We approached the goal of applying meta-learning to self-supervised masked autoencoders for spatiotemporal learning in three steps. Broadly, we seek to understand the impact of applying meta-learning to existing state-of-the-art…

Compressed Sensing MRI (CS-MRI) has provided theoretical foundations upon which the time-consuming MRI acquisition process can be accelerated. However, it primarily relies on iterative numerical solvers which still hinders their adaptation…

Masked Image Modeling (MIM) is a technique in self-supervised learning that focuses on acquiring detailed visual representations from unlabeled images by estimating the missing pixels in randomly masked sections. It has proven to be a…

Referring Image Segmentation (RIS) aims to segment the object in an image uniquely referred to by a natural language expression. However, RIS training often contains hard-to-align and instance-specific visual signals; optimizing on such…

Learning robust representations across extremely heterogeneous modalities remains a fundamental challenge in multi-modal vision. As a critical and profound instantiation of this challenge, high-resolution (HR) joint optical and synthetic…

Recently, self-supervised learning methods like MoCo, SimCLR, BYOL and SwAV have reduced the gap with supervised methods. These results have been achieved in a control environment, that is the highly curated ImageNet dataset. However, the…

Recovering 3D geometry and textures of individual objects is crucial for many robotics applications, such as manipulation, pose estimation, and autonomous driving. However, decomposing a target object from a complex background is…

Recent image degradation estimation methods have enabled single-image super-resolution (SR) approaches to better upsample real-world images. Among these methods, explicit kernel estimation approaches have demonstrated unprecedented…

Tremendous efforts have been made on document image rectification, but how to learn effective representation of such distorted images is still under-explored. In this paper, we present DocMAE, a novel self-supervised framework for document…

Token compression is crucial for mitigating the quadratic complexity of self-attention mechanisms in Vision Transformers (ViTs), which often involve numerous input tokens. Existing methods, such as ToMe, rely on GPU-inefficient operations…

Learning-based lossless image compression employs pixel-based or subimage-based auto-regression for probability estimation, which achieves desirable performances. However, the existing works only consider context dependencies in one…

Self-supervised learning has been a powerful training paradigm to facilitate representation learning. In this study, we design a masked autoencoder (MAE) to guide deep learning models to learn electroencephalography (EEG) signal…

In view of the fact that semi- and self-supervised learning share a fundamental principle, effectively modeling knowledge from unlabeled data, various semi-supervised semantic segmentation methods have integrated representative…

Deeper Vision Transformers (ViTs) are more challenging to train. We expose a degradation problem in deeper layers of ViT when using masked image modeling (MIM) for pre-training. To ease the training of deeper ViTs, we introduce a…

Raman spectroscopy serves as a powerful and reliable tool for analyzing the chemical information of substances. The integration of Raman spectroscopy with deep learning methods enables rapid qualitative and quantitative analysis of…

Magnetic resonance imaging (MRI) is a crucial medical imaging modality. However, long acquisition times remain a significant challenge, leading to increased costs, and reduced patient comfort. Recent studies have shown the potential of…